skills.rest
calesthio
calesthioCOMMUNITY
Explore all skills by this author →
𝕏@calesthioailabsGitHub

google-cloud-vision

Extract labels, OCR, colors, and crop hints from still images via Cloud Vision.

123|21|Updated Jul 11, 2026
Search Tags:#ocr#document processing#image analysis#cloud storage#safe search#google cloud vision#object localization
One-click install
npx skills add https://github.com/calesthio/generative-media-skills --skill google-cloud-vision
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: google-cloud-vision
Source: https://github.com/calesthio/generative-media-skills/tree/main/skills/providers/image-understanding/google-cloud-vision
Command: npx skills add https://github.com/calesthio/generative-media-skills --skill google-cloud-vision

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps agents extract reliable, structured information from still images without relying on open-ended visual reasoning. It supports production workflows that need searchable labels, object locations, OCR, moderation signals, color data, crop suggestions, and web-reference evidence.

Core Features & Use Cases

  • Structured Image Analysis: Detect labels, objects, dominant colors, crop hints, explicit-content likelihoods, and web matches.
  • OCR and Document Processing: Choose sparse-text detection for signs, labels, and screenshots or document-text detection for dense pages, handwriting, PDFs, and TIFFs.
  • Production Pipelines: Design synchronous and asynchronous Cloud Storage workflows with IAM, quotas, cost estimation, regional OCR endpoints, retention controls, retries, and quality evaluation.
  • Use Case: Process a large media library with searchable tags, object boxes, poster-text OCR, and SafeSearch-based review routing while preserving auditability and human oversight.

Quick Start

Use the google-cloud-vision skill to analyze the uploaded still images for labels, object locations, poster text, explicit-content review signals, and production QA recommendations.

Frequently Asked Questions about google-cloud-vision

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract text from PDFs and TIFFs using OCR?▼

OCR for dense PDFs and TIFFs uses document-text detection to process dense pages and handwriting. You choose between sparse-text detection for signs and screenshots or document-text detection for multi-page files.

What is the best way to moderate images for explicit content?▼

Image moderation evaluates explicit-content likelihoods using Safe Search signals. This routes media-library assets for human review based on detected Safe Search flags while preserving auditability.

Can I batch process images stored in Cloud Storage?▼

Cloud Storage batch processing supports asynchronous workflows for large media libraries. You design synchronous and asynchronous pipelines with IAM, quotas, regional OCR endpoints, and retention controls.

Does Google Cloud Vision work for object localization and tagging?▼

Object localization and tagging detect labels, objects, and bounding boxes within still images. This structured annotation extracts reliable searchable tags and object locations without relying on open-ended visual reasoning.

How do I plan quotas and costs for image analysis pipelines?▼

Quota and cost planning for image analysis pipelines involves estimating synchronous and asynchronous processing volumes. You configure IAM, regional OCR endpoints, and quality evaluation to manage production limits.

When should I use sparse-text detection versus document-text detection?▼

Sparse-text detection handles signs, labels, and screenshots, while document-text detection processes dense pages, handwriting, PDFs, and TIFFs. You choose the OCR mode based on the visual density of the source media.

Related Skills

Explore More Software Engineering Skills→
awsaws
2.3k

securing-s3-buckets

Secure S3 buckets with access control, encryption, logging, and monitoring.

Official
Advanced
leonanpereirapintoleonanpereirapinto
1

docling

Convert PDFs, Word, HTML, and images into structured Markdown, JSON, or HTML output.

Community
Intermediate
686f6c61686f6c61
105

code-review

Review code for quality, readability, logical correctness, and error handling.

Community
Advanced
software-mansionsoftware-mansion
1.7k

react-native-executorch

Integrate on-device AI models into React Native applications using ExecuTorch.

Official
Advanced